Reading the city through its neighbourhoods: Deep text embeddings of Yelp reviews as a basis for determining similarity and change

Abstract

This paper develops novel methods for using Yelp reviews as a window into the collective representations of a city and its neighbourhoods. Basing analysis on social media data such as Yelp is a challenging task because review data is highly sparse and direct analysis may fail to uncover hidden trends. To this end, we propose a deep autoencoder approach for embedding the language of neighbourhood-based business reviews into a reduced dimensional space that facilitates similarity comparison of neighbourhoods and their change over time. Our model improves performance in distinguishing real and fake neighbourhood descriptions derived from real reviews, increasing performance in the task from an average accuracy of 0.46 to 0.77. This improvement in performance indicates that this novel application of embedded language analysis permits us to uncover comparative trends in neighbourhood change through the lens of their venues' reviews, providing a computational methodology for reading a city through its neighbourhoods. The resulting toolkit makes it possible to examine a city's current sociological trends in terms of its neighbourhoods' collective identities.

Jumpstarting the Justice Disciplines: A Computational-Qualitative Approach to Collecting and Analyzing Text and Image Data in Criminology and Criminal Justice Studies

“…We have demonstrated how qualitative logics of inquiry and skill sets can be folded into computational research. We have demonstrated this by showing some of the iterative steps involved in using computational approaches to examine police communications in ways that cannot be fully automated, and which complement the 'thinner' insights of quantitative methods with the 'thicker' insights of qualitative ones (Bornakke and Due 2018;Jemielniak 2020;Olson et al 2021).…”

“…Both quantitative and qualitative research skills and logics are often required when working with computational techniques. Computational approaches to research can help bridge these cultures by productively and creatively drawing from both traditions (Bornakke and Due 2018;Brandt and Timmermans 2021;Jemielniak 2020;Mills 2018;Olson et al 2021). The desirability of small samples for some types of research and some research questions (Benfer 1968;Small 2009) is not incompatible with computational approaches.…”

Complex causal structures of neighbourhood change: Evidence from a functionalist model and yelp data

“…Zukin, Lindeman and Hurson [49] identify racial bias by manually coding Yelp reviews of restaurants in two gentrifying neighbourhoods -one predominantly Black and another predominantly White. Olson et al [50] use computational text analysis techniques to "read the city" via Yelp reviews, revealing collective representations across neighbourhoods and identifying patterns of continuity and change among them.…”

GIScience and neighborhood change: Toward an understanding of processes of change

“…Since then, predictive improvements have been made by capitalizing on machine learning methods and novel, especially user‐generated or microgeographic, data sources. Efforts in “nowcasting” or associating gentrification with Yelp data reviews and business types (Glaeser, Kim, & Luca, 2018; Olson, Calderon‐Figueroa, Bidian, Silver, & Sanner, 2021), Instagram postings (Han, Hong, & Lee, 2020), Foresquare check‐ins (Arribas‐Bel & Bakens, 2019), and restaurant reviews (Dong, Ratti, & Zheng, 2019) have advanced the recent state of the art. The use of more traditional government statistics has also been blended with more sophisticated methods such as random forests to better predict gentrification (Reades, De Souza, & Hubbard, 2019).…”